1 / 28

Artificial Neural Networks - Introduction -

Artificial Neural Networks - Introduction -. Overview. Biological inspiration Artificial neurons and neural networks Why use ANN? ANN Characterization. Biological inspiration.

Download Presentation

Artificial Neural Networks - Introduction -

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Artificial Neural Networks- Introduction -

  2. Overview • Biological inspiration • Artificial neurons and neural networks • Why use ANN? • ANN Characterization

  3. Biological inspiration Animals are able to react adaptively to changes in their external and internal environment, and they use their nervous system to perform these behaviours. An appropriate model/simulation of the nervous system should be able to produce similar responses and behaviours in artificial systems. The nervous system is build by relatively simple units, the neurons, so copying their behavior and functionality should be the solution.

  4. Action potential

  5. Biological inspiration

  6. Biological inspiration dendrites axon synapses

  7. Biological inspiration Dendrites: Input Axon: Output Soma : Cell Body The information transmission happens at the synapses.

  8. Artificial neurons Neurons work by processing information. x1 x2 x3 … xn-1 xn w1 Output w2 Inputs y w3 . . . wn-1 wn The McCullogh-Pitts model

  9. Artificial neural network (ANN) • is a mathematical model or computational model based on biological neural networks • Artificial Neural Network consists of neurons arranged in layers • Neurons act as parallel processor • Neurons are connected with each other vi connection. • there are weights associated with connections • Implementation: • Learning • testing

  10. Artificial neural networks Output Inputs An artificial neural network is composed of many artificial neurons that are linked together according to a specific network architecture. The objective of the neural network is to transform the inputs into meaningful outputs.

  11. Artificial neural networks • Dendrites: Input Layer • Axon : Output Layer • Soma: Net( weighted sum of input y_in) and activation function • Synapse: Weights

  12. Why use ANN? -Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience. -Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time. -Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability. -Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage.

  13. ANN Characterization • ANN can be characterized by: • Activation function • Weights Adjustment (learning algorithm) • Architecture

  14. Activation function • Function to map weighted sum of input into output • Determine whether neuron fires or not • Linear function (Identity) • F(y_in)=y y_in (weighted sum of input) y (output) • Step function • y=f(y_in)=

  15. Activation function • Logistic or sigmoid function • Binary sigmoid • F(y_in)= • Bipolar Sigmoid • F(y_in)=

  16. Learning Algorithm • Learning in ANN is Weights adjustment to • get desired output • To minimize the error • To gain more experience • Learning • Supervised • unsupervised

  17. Supervised Learning • There is supervisor during learning process • Input and output are known • The job of ANN is to classify any new input according to known classes • Example : teaching baby the difference pens and other things • LVQ (learning vector quantization)

  18. Unsupervised learning • Input known but output unknown • The classes are unknown to ANN • Job of ANN is to find similarities between input and divide them into categories (cluster) • SOM (Self organizing map)

  19. Architecture • Show the number of layer in Neural Network • Show the number of neurons in each layer • Show how neurons connect to each other

  20. Architecture • Feed forward • allow signals to travel one way only; from input to output. • There is no feedback (loops) Multi layer

  21. Architecture • Feedback networks • signals travelling in both directions by introducing loops in the network

  22. linearly separable problem • A linearly separable problem is one in which the classes can be separated by a single hyperplane • It is often the case that a problem is not linearly separable. To solve these we use a Multi-Layer Perceptron (MLP) where one layer feeds into the next.

  23. XOR problem

  24. XOR problem

  25. The shape of regions in pattern space that can be separated by a Multi-Layer Perceptron

  26. back-propagation • Last time we saw that the delta rule can be used to train a perceptron. When training the MLP, the error (delta) must be propagated back through the layers. This is called error back-propagation. Or just backpropagation.

  27. Thanks

More Related